© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92518
    Prev
    Next
    INDEX
    Explanations

    Deputy followed by titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     stren
    -0.09
    eil
    -0.08
    e
    -0.08
     Dw
    -0.08
    eer
    -0.08
    es
    -0.08
     Sanford
    -0.07
    arda
    -0.07
     fr
    -0.07
     agre
    -0.07
    POSITIVE LOGITS
     Bash
    0.11
    sv
    0.11
    antee
    0.11
    svp
    0.10
    uby
    0.10
    à¸ĩ
    0.10
    otope
    0.10
    ÑģÑı
    0.10
    uncio
    0.10
    uala
    0.10
    Activations Density 0.002%

    No Known Activations